Masking the Gaps: An Imputation-Free Approach to Time Series Modeling with Missing Data

Abstract

A significant challenge in time-series (TS) modelling is presence of missing values in real-world TS datasets. Traditional two-stage frameworks, involving imputation followed by modeling, suffer from two key drawbacks: (1) the propagation of imputation errors into subsequent TS modeling, (2) the trade-offs between imputation efficacy and imputation complexity. While one-stage approaches attempt to address these limitations, they often struggle with scalability or fully leveraging partially observed features. To this end, we propose a novel imputation-free approach for handling missing values in time series termed \textbf{Miss}ing Feature-aware \textbf{T}ime \textbf{S}eries \textbf{M}odeling (\textbf{MissTSM}) with two main innovations. \textit{First}, we develop a novel embedding scheme that treats every combination of time-step and feature (or channel) as a distinct token. \textit{Second}, we introduce a novel \textit{Missing Feature-Aware Attention (MFAA) Layer} to learn latent representations at every time-step based on partially observed features. We evaluate the effectiveness of MissTSM in handling missing values over multiple benchmark datasets.